Quantitative Analysis of Soil Total Nitrogen Using Hyperspectral Imaging Technology with Extreme Learning Machine.

Hongyang Li,Shengyao Jia,Zichun Le

doi:10.3390/s19204355

Abstract

Soil nutrient detection is important for precise fertilization. A total of 150 soil samples were picked from Lishui City. In this work, the total nitrogen (TN) content in soil samples was detected in the spectral range of 900–1700 nm using a hyperspectral imaging (HSI) system. Characteristic wavelengths were extracted using uninformative variable elimination (UVE) and the successive projections algorithm (SPA), separately. Partial least squares (PLS) and extreme learning machine (ELM) were used to establish the calibration models with full spectra and characteristic wavelengths, respectively. The results indicated that the prediction effect of the nonlinear ELM model was superior to the linear PLS model. In addition, the models using the characteristic wavelengths could also achieve good results, and the UVE–ELM model performed better, having a correlation coefficient of prediction (rp), root-mean-square error of prediction (RMSEP), and residual prediction deviation (RPD) of 0.9408, 0.0075, and 2.97, respectively. The UVE–ELM model was then used to estimate the TN content in the soil sample and obtain a distribution map. The research results indicate that HSI can be used for the detection and visualization of the distribution of TN content in soil, providing a basis for future large-scale monitoring of soil nutrient distribution and rational fertilization.

Highlights

Soil is an important part of agricultural production
The Partial least squares (PLS) and the extreme learning machine (ELM) models were established with spectral data in the full spectra of each sample in the calibration set, the two models were each used to predict the total nitrogen (TN) content of all samples in the prediction set
Shen et al used the PLS model combined with uninformative variable elimination (UVE) and successive projections algorithm (SPA) to estimate the soil carbon content on NIR spectroscopy, and the results showed that UVE and SPA were beneficial and necessary for soil carbon modeling on NIR spectroscopy [37]

Summary

Introduction

Soil is an important part of agricultural production. Scientific fertilization according to the richness or poorness of nutrients in the soil is the basis for high-quality and high-yield crops [1]. Fertilization is often done blindly or mechanically in order to obtain a high yield, resulting in the uneven distribution and low utilization of chemical fertilizers. Excessive nitrogen fertilizer use reduces the rate of fertilizer utilization and causes economic losses and causes serious environmental pollution and excessive nutrient content in crops [2]

Methods

Results

Conclusion